•  
  •  
 

Applied Mathematics & Information Sciences

Author Country (or Countries)

Egypt

Abstract

The substantial number of false positives in X-ray analysis of images is one of the current problems, which causes delays and adds to the responsibilities of security staff. Maintaining security measures to confront growing threats and new technology is a continuing concern. Using a Convolutional Neural Network-Gated Recurrent Unit (CNN-GRU) model, this research suggests a novel strategy for upgrading the safety precautions at Kuwait International Airport. This research tackles the requirement for more precise and efficient threat detection, which is crucial for airport security. Utilizing the advantages of CNNs and GRUs is the goal of the CNN-GRU approach. The GRU, a recurrent neural network, can evaluate the ordered sequence of X-ray scans and keep context across time. At the same time, the CNN element is skilled at extracting features and can interpret X-ray images to identify potential hazards. With the help of this communication, the model is better equipped to identify hidden risks and is more accurate. This research involves a thorough analysis of the effectiveness of the suggested model via intensive training and testing. The findings show that the CNN-GRU model works better than traditional approaches in recognizing threats in X-ray pictures, considerably lowering false positives and increasing safety precautions at Kuwait International Airport. The CNN-GRU model’s deployment reflects an innovative approach to security at airports, offering a reliable and flexible instrument to protect passengers and staff successfully. This study contributes to continuing attempts to maintain and improve airport security in a threat environment that is always changing.

Digital Object Identifier (DOI)

https://dx.doi.org/10.18576/amis/180103

Download

Share

COinS